METR general autonomy task suite
Only in system cards
Agents complete multi-step tasks in virtual environments. Scored as horizon weighted average task completion compared with human time limits.
Precursor of the METR time horizon suite. OpenAI cards show it as a chart.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
4
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for METR general autonomy task suite yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
4 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 5 Dec 2024 | o1 system card | METR Agent Performance on Test Suite, weighted average score, chart without printed numbers (Figure 3, 4.4.4) | Autonomy | |
| 12 Sep 2024 | o1-preview system card | METR Agent Performance on General Autonomy Benchmark, chart without printed numbers (Figure 3, 3.3.2) | Autonomy | |
| 12 Sep 2024 | o1-mini system card | METR Agent Performance on General Autonomy Benchmark, chart without printed numbers (Figure 3, 3.3.2) | Autonomy | |
| 8 Aug 2024 | GPT-4o system card | METR assessment, fraction of 86 tasks completed (weighted) vs humans with time limits, chart without printed numbers (4.1, Figure) | Autonomy |
More in AI research
- MLS-Bench In use Agent must invent one algorithmic change in an ML research scaffold whose gain transfers across settings. Scored relative to human baselines. Claude Fable 5.1 50.3%
- PaperBench In use Agent replicates ICML 2024 papers from scratch. LLM judge grades against author-written hierarchical rubrics.
Qwen 3.8 Max 93% - MLE-bench In use Kaggle-style ML engineering competitions. Agent trains models and is scored against competition leaderboards. GPT-6 Astra 93.8%
- PostTrainBench 1.2 In use CLI agent gets a base model, one H100 and a time budget to post-train it for a target benchmark. Scored on normalized gain. Claude Fable 5.1 44.6%
- KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup.
MiniMax-M3 28.8% - OpenAI PRs Only in system cards Agents replicate internal OpenAI pull requests from a pre-PR branch and a prompt. Graded by hidden unit tests as pass@1. GPT-5.2 55%